Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 1907.06302

Compound TCP with Random Early Detection (RED): stability, bifurcation and performance analyses

Sreelakshmi Manjunath·Gaurav Raina
View original source ↗Read source document ↗Export metadata ↓

Abstract

The problem of increased queueing delays in the Internet motivates the study of currently implemented transport protocols and active queue management (AQM) policies. We study Compound TCP (default protocol in Windows) with Random Early Detection (RED). RED uses an exponentially weighted moving average of the queue size to make packet-dropping decisions, aiming to control the queue size. One must study RED with current protocols in order to explore its viability in the context of increased queueing delays. We derive a non-linear time-delayed model for Compound TCP-RED. We derive a sufficient condition for local stability of this model, and examine the impact of (i) round-trip time (RTT) of the TCP flows, (ii) queue averaging parameter and (iii) packet-dropping thresholds. Further, we establish that the system undergoes a Hopf bifurcation as any of the above parameters is varied. This suggests the emergence of limit cycles in the queue size, which may lead to synchronisation of TCP flows and loss of link utilisation. Next, we study a regime where queue size averaging is not performed, and packet-dropping decisions are based on instantaneous queue size. In this regime, we derive the necessary and sufficient condition for local stability. A comparison of the stability results for Compound TCP-RED in the two regimes--with and without queue size averaging--reveals that averaging may not be beneficial to system stability. Packet-level simulations show that the queue size indeed exhibits limit cycle oscillations as system parameters are varied. We then outline a simple threshold-based queue policy, that could ensure stable low-latency operation. We show that the threshold policy outperforms RED in terms of queueing delay, flow completion time and packet loss. We highlight that the threshold-based policy could mitigate the issue of increased queueing delays in the Internet.

Explore related subjects

cs.NIcs.SYeess.SY

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Sreelakshmi Manjunath, Gaurav Raina. 2019-07-15. Compound TCP with Random Early Detection (RED): stability, bifurcation and performance analyses. https://arxiv.org/abs/1907.06302

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Semord: Learned Semantic-Preserving Placement and Low-Fanout Routing for Distributed Vector Search

Vector databases are increasingly deployed in distributed settings where different users, sites, or domains maintain vector data. Existing vector databases rely on a coordinator to record which shards store which parts of the vector space and to route each query to those shards. In a decentralized setting, peers may join, leave, or move data without a trusted node tracking every change, and outdated routing information can therefore send queries to the wrong peers or require contacting many peers, reducing vector retrieval recall and increasing network latency. We present Semord, a decentralized vector search overlay system that achieves high recall by routing each ANN query to a small set of relevant peers, without relying on a centralized coordinator. Semord addresses this problem by making semantic locality routable: 1) We propose VHash to place semantically related vectors near each other in the overlay key space while avoiding load imbalance, so that each query only needs to contact a small neighborhood of peers for distributed local ANN ranking. 2) We design VecDHT, a communication protocol that maintains decentralized routing, region metadata, churn resilience, and VHash updates under membership and workload changes. Our extensive experiments on a real testbed show that Semord improves recall by more than 15% and reduces contacted peers by over 60% compared with decentralized baselines. Semord also approaches the recall and latency of a centralized oracle baseline while reducing peak peer-local ANN index memory by more than 2X. Controlled large-scale simulations further show that Semord scales across real-world embedding workloads and remains robust under churn for scoped vector retrieval as a decentralized overlay.

cs.NI↗
arXiv2026

Lizard: Bandwidth-Adaptive Real-Time Video Analytics through Content-Aware Packet Discarding at Last-Mile Edge Routers

The timeliness and accuracy of edge-based video analytics can be hindered by drastic reductions in available bandwidth (ABW) at last-mile edge routers, causing prolonged queuing delays. This work proposes Lizard, a system that leverages video-content-aware packet discarding to mitigate the negative effects of drastic ABW degradation that may frequently occur at a last-mile edge router by judiciously discarding packets that contain frame blocks less important to the analytics at the destination. To achieve this, we first devise a frame-block-aware RTP header extension to effectively decouple packet dependencies to encode frame blocks. Second, Lizard uses a priority-based feedback mechanism that dynamically evaluates packet priorities based on relative accuracy impacts. Third, we develop an adaptive phase-transition-based packet discarding strategy at the router to discard packets that represent unimportant blocks. Our evaluation of Lizard shows improvements over existing methods are substantial: 53.2% reduction in latency and 27.1% increase in analysis accuracy.

cs.NI↗
arXiv2026

Flux: Optimal Scheduling of Optical Circuit Switches for LLM Training

Optical Circuit Switching (OCS) offers high bandwidth density and energy efficiency for LLM training, but incurs a non-negligible reconfiguration delay. Prior work typically schedules optical circuit switches independently of compute, using aggregate traffic demand to determine which circuits to provision and when. We argue that this separation creates a fundamental inefficiency: reconfigurations that ignore the compute timeline can stall communication, resulting in low circuit utilization and large buffer requirements. In this paper, we present Flux, a scheduler that optimally schedules optical circuit switches based on the structure of the entire workload. Flux remains effective across a wide range of switching speeds by reusing circuits and amortizing reconfiguration delay behind compute and communication. We show that Flux reduces training iteration time by up to $10\times$ and peak NIC buffer requirements by more than three orders of magnitude compared to traditional periodic schedulers.

cs.NI↗